OpenMixup: A Comprehensive Mixup Benchmark for Visual Classification
Data mixing, or mixup, is a data-dependent augmentation technique that has greatly enhanced the generalizability of modern deep neural networks. However, a full grasp of mixup methodology necessitates a top-down hierarchical understanding from systematic impartial evaluations and empirical analysis, both of which are currently lacking within the community. In this paper, we present OpenMixup, the first comprehensive mixup benchmarking study for supervised visual classification. OpenMixup offers a unified mixup-based model design and training framework, encompassing a wide collection of data mixing algorithms, a diverse range of widely-used backbones and modules, and a set of model analysis toolkits. To ensure fair and complete comparisons, large-scale standard evaluations of various mixup baselines are conducted across 12 diversified image datasets with meticulous confounders and tweaking powered by our modular and extensible codebase framework. Interesting observations and insights are derived through detailed empirical analysis of how mixup policies, network architectures, and dataset properties affect the mixup visual classification performance. We hope that OpenMixup can bolster the reproducibility of previously gained insights and facilitate a better understanding of mixup properties, thereby giving the community a kick-start for the development and evaluation of new mixup methods. The source code and user documents are available at \url{https://github.com/Westlake-AI/openmixup}.
PDF Abstract
CIFAR-10
ImageNet
CIFAR-100
Fashion-MNIST
CUB-200-2011
STL-10
Places205
iNaturalist
FGVC-Aircraft
